6 days ago · From Generalization Analysis to Optimization Designs for State Space Models ... A State Space Model (SSM) is a foundation model in time series analysis ...

Jul 14, 2024 · In this paper, we investigate the long-term memory learning capabilities of state-space models (SSMs) from the perspective of parameterization. We prove that ...

Jul 11, 2024 · This paper studies sequence modeling for prediction tasks with long range depen- dencies. We propose a new formulation for state space models (SSMs) based ...

Jul 21, 2024 · In optimizing space deployable structures, many researchers adapted multi-objective optimization frameworks combining analysis models (AMs) and genetic ...

Jul 13, 2024 · In this work, we develop a stronger characterization of the optimization and generalization ... state-space model. Under a suitable correlated design assumption, ...

Jul 17, 2024 · Introducing pretraining-finetuning for rapid task-specific accuracy improvement. •. Significant potential in fast airfoil flow simulation and optimizing shape ...

Jul 1, 2024 · We demonstrate our method for paradigmatic frustrated spin-1/2 models on square and triangular lattices, for which our trained deep networks approach machine ...

Jul 16, 2024 · Although a quantum computer can efficiently compute the quantum state feature space representation ... generalization of its models. The approaches based ...

Jul 8, 2024 · LEARNING QUANTUM-STATE PROPERTIES IN REPRODUCING KERNEL HILBERT SPACE (RKHS). Now we further elaborate the kernel model and exploit the theory of generalization ...

Jul 14, 2024 · In the paper, we design a novel functional Wasserstein variational policy optimization (FWVPO) based on the Wasserstein distance between function distributions.